AI Paper Atlas

Research map / Video / Video generation

VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos

Qiucheng Wu, Handong Zhao, Zhixin Shu, Jing Shi, Yang Zhang, Shiyu Chang

ICML 2026 · Video › Video generation · approach: Diffusion-based human image animation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add appearance LoRA during training (ablation)ViVidCam · Human study ablationAction Correctness: 0.75 -> 0.93Improved
add appearance LoRA during training (ablation)ViVidCam · Human study ablationRealism: 0.60 -> 0.74Improved
add temporal consistency loss (ablation)ViVidCam · Human study ablationAction Correctness: 0.57 -> 0.93Improved
add temporal consistency loss (ablation)ViVidCam · Human study ablationRealism: 0.76 -> 0.74Hurt
add style-aligned prompts (ablation)ViVidCam · Human study ablationRealism: 0.65 -> 0.74Improved
add style-aligned prompts (ablation)ViVidCam · Human study ablationAction Correctness: 0.93 -> 0.93No clear effect
add A-LoRA, A-LoRA dropped at inference, over only dual adaptation (ablation)ViVidCam · Human study ablationRealism: 0.61 -> 0.74Improved
keep appearance LoRA at inference (ablation)ViVidCam-Cog · Inference ablationFVD: 1866.40 -> 2097.61Hurt
keep appearance LoRA at inference (ablation)ViVidCam-AC3D · Inference ablationFVD: 1721.45 -> 2156.02Hurt
raise temporal loss weight from 0.03 to 0.3 (ablation)ViVidCam-Cog · Lambda sweepTransErr: 0.5859 -> 0.4011Improved
raise temporal loss weight from 0.3 to 3 (ablation)ViVidCam-Cog · Lambda sweepFVD: 1866.40 -> 2124.11Hurt
add RealEstate10K real videos to synthetic training (ablation)ViVidCam trajectory-based · RealEstate10K-based settingAction Correctness: 0.91 -> 0.88No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy